Benchmark #1814

Download
Elden Ring: COSMOS vs COSMOS-NEXT

GPU Limited static scene + CPU Decoded YouTube Video | 30 second frame recording with 0ms interval | Performance Governor/EPP | Proton GE 10.17 Wayland Native | SCX Main: 833e8fa Next: 5c739b9 | kernel-cachyos-lto-6.17.0-cachyos1.lto.fc44.x86_64 with Staging SCX Patches.

Submitted 2 weeks ago by summedkibbles36

Specifications
Label OS GPU CPU RAM OS specific
Main -m all -c 0 -p 0 | 1 Steam Runtime 3 (sniper) AMD Radeon RX 7900 GRE (RADV NAVI31) AMD Ryzen 7 7800X3D 8-Core Processor 33 GB 6.17.0-cachyos1.lto.fc44.x86_64 performance
Main -m all -c 0 -p 0 | 2 Steam Runtime 3 (sniper) AMD Radeon RX 7900 GRE (RADV NAVI31) AMD Ryzen 7 7800X3D 8-Core Processor 33 GB 6.17.0-cachyos1.lto.fc44.x86_64 performance
Next -m all -c 0 -p 0 | 1 Steam Runtime 3 (sniper) AMD Radeon RX 7900 GRE (RADV NAVI31) AMD Ryzen 7 7800X3D 8-Core Processor 33 GB 6.17.0-cachyos1.lto.fc44.x86_64 performance
Next -m all -c 0 -p 0 | 2 Steam Runtime 3 (sniper) AMD Radeon RX 7900 GRE (RADV NAVI31) AMD Ryzen 7 7800X3D 8-Core Processor 33 GB 6.17.0-cachyos1.lto.fc44.x86_64 performance
# Top runs: * **Highest FPS**: `Main -m all -c 0 -p 0 | 1` and `Next -m all -c 0 -p 0 | 1` offer very close performance but `Main -m all -c 0 -p 0 | 1` is slightly ahead in FPS. * **Smoothest FPS**: `Main -m all -c 0 -p 0 | 1` due to its lowest standard deviation and variance. * **Best overall**: `Main -m all -c 0 -p 0 | 1` combines both high FPS and smoothness. # Summary This benchmark compares the performance of COSMOS and COSMOS-NEXT using `Proton GE 10.17` under `Wayland Native` in a 30-second frame recording. Both configurations employ the `cachyos-lto` Linux kernel with `Staging SCX Patches` and test on identical hardware setups. The `COSMOS` setup consistently offers slightly higher FPS and smoother performance compared to `COSMOS-NEXT`, indicating superior optimization in handling static scenes while decoding video during the benchmark scenario. The performance differences, while notable, are subtle and primarily evident in minor discrepancies in the frame timing and frame stability metrics.